A Network Anomaly Intrusion Detection Method Based on Ensemble Learning for Library e-Learning Platform

Abstract

E-learning is an important part of the library service and a direction of transformation for libraries. How to ensure the security of e-learning platforms is a key point that cannot be ignored in the construction. Although machine learning has been widely used in network anomaly detection, traditional machine learning methods have problems such as over-reliance on manual feature extraction, dimension disaster, etc., and it is difficult to achieve effective prediction of potential threats in practical applications. To solve these problems, this paper proposes a network anomaly intrusion detection method based on ensemble learning to effectively ensure the network security of the e-learning platform. Combined with the concept of ensemble learning, simple decision tree is used as the base class learner, and by combining multiple models into a stronger model, the random forest method is used to improve the ability to identify anomaly network attacks. After experimental verification, various performance evaluation indicators and ROC curves of the experimental results show that the algorithm can effectively identify both normal network access and abnormal network access. Therefore, this method can be applied to the library e-learning platform, which can provide learners with rich and convenient online learning services, and at the same time effectively ensure the network security of the platform.